PPL
Guang Yang
Papers (8)
Rubato: Transcribing Piano Music with TimestampsA Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime VariabilityBehavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference PredictionBehavior-Induced Mirror-Prox Temporal-Difference Learning for Faster Off-Policy PredictionAsking Back: Interaction-Layer Antidistillation WatermarksTowards Fine-Grained and Verifiable Concept Bottleneck ModelsTaming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual GenerationAutoregressive Visual Generation Needs a Prologue